Developer
Build and self-host
Install the MIT-licensed engine, record the bundled app, compile it, lint and certify the bundle, then replay it locally. No account or hosted service is required.
OpenAdapt.AI
LOCAL-FIRST · MIT OPEN SOURCE1.6k stars on OpenAdapt· 258 forks
Compile repeated GUI work into governed, deterministic workflows.
Demonstrate a bounded, repeated GUI workflow. Compile it into a locally executable workflow whose healthy replay makes no model calls. When the interface changes, OpenAdapt re-resolves from retained evidence, proposes a governed repair, or halts for an operator.
Use the same compiled workflow model across browser, Windows, macOS, Linux, RDP, Citrix, and VDI targets, running locally, through OpenAdapt Cloud, or inside a customer-controlled boundary. Browser workflows are proven today; Windows and macOS are experimental, and remote-display targets (RDP, Citrix, VDI) are research-stage. See how deployment works.
1.0click'Sign In'template12ms✓
2.0typeusername—8ms✓
3.0click'Tasks'template9ms✓
4.0click'Open referral'template11ms✓
5.0click'Save Encounter'⚠ UI drift detected
└ re-resolved via geometry — anchor update saved as diff
postconditions verified · run complete
total 2.4s · model calls: 0 · cost per run: $0.00VERIFIED · 0 MODEL CALLS
Choose your path
One engine, three launch paths
Automation & operations
Launch a managed workflow
Bring one repeated GUI workflow, its operating boundary, and an independent success oracle. OpenAdapt compiles the demonstrated last mile and keeps its run evidence, review, and repair lifecycle connected.
Regulated enterprise
Deploy inside a trusted boundary
Define identity coverage, effect verification, artifact sanitization, and the runtime data boundary for a consequential workflow before it enters production.
OpenAdapt Cloud
From approved workflow to reviewable outcome.
Explore how workflows, runs, evidence, and reports stay connected across three real reference applications.
OpenAdaptCloud
Reference workflows
Healthcare reference
OpenEMR
Reference workflow
Patient note entry
A demonstrated OpenEMR task compiled into an inspectable, governed workflow.
- Workflow
- openemr-browser-reference
- Inputs
- Workflow-defined parameters
- Target
- Bounded OpenEMR browser task
- Effect contract
- One matching note persisted
Real OpenAdapt Cloud app · synthetic OpenEMR workflowProcess
How it works
A demonstrated task becomes a reviewable program, not a prompt that a model reinterprets on every run.
Choose a workflow and execution environment independently.
Reference workflow
Execution environment
Healthcare × BrowserRecorded and replayed OpenEMR footage for a bounded healthcare browser workflow. View the bounded use case →
Structural browser execution with DOM targets, deterministic input, and configured effect checks.Selected application footage with the browser execution path in context.
Every stage uses the selected reference application. Application footage and execution-environment overlays are labeled separately.
- 1.0
Record
Demonstrate one bounded instance. OpenAdapt captures the screen, input, and available structural evidence needed to compile it.
Record — real footage · driving a live OpenEMR instanceBrowser execution · selected application footage - 2.0
Compile
Your recording becomes a script you can read, edit, and reuse.
workflow.jsoninspectable- workflow
- openemr-browser-reference
- parameters
- workflow-defined inputs
- target
- bounded OpenEMR browser task
- effect
- deployment-specific oracle required
compile — OpenEMR demonstrationSelected-app footage with an animated view of the inspectable workflow OpenAdapt produces.Browser execution · selected application footage - 3.0
Replay
Healthy runs execute the compiled steps locally without a model call.
Run — real footage · driving a live OpenEMR instanceBrowser execution · selected application footage - 4.0
Resolve or halt
Under drift, deterministic evidence re-finds the target, an optional model proposes a repair, or verification refuses to continue.
target evidenceunique match required- 01Recorded OpenEMR target evidence
- 02Configured identity and target constraints
- 03Unique actionable match required
ambiguous or unverifiableHALT · REVIEWresolve or halt — OpenEMR replaySelected-app replay footage with the target-evidence ladder and explicit halt path animated in context.Browser execution · selected application footage - 5.0
Verify and report
Configured postconditions and effects are checked, and every run records what happened, changed, or halted.
run auditqualification required- Recorded mediarecord and compiled-replay footage
- Effect oraclenot established by this media
- Identity policymust be configured for the workflow
- Acceptancehalt until declared checks pass
No application-specific audit result claimedaudit — OpenEMR replayQualification contract for the OpenEMR reference. The footage does not establish an independent effect audit or production EMR reliability.Browser execution · selected application footage
UI drift
What “repair” means, and where it stops
OpenAdapt is not an unconstrained agent. Drift ends in one of four explicit outcomes, each visible in the run report.
Automatic
Deterministic re-resolution
Structure, templates, OCR, and geometry try to re-find the recorded target. No model is required. A changed anchor is saved as an auditable bundle diff.
Optional
AI-assisted proposal
If deterministic evidence is insufficient and a model is configured, it can propose a target or confirm limited visual state. The model can be wrong; identity, policy, and postcondition gates still decide whether execution continues.
Operator path
Human teaching and resume
A halt produces evidence for an operator. The CLI can teach a correction, and durable mode can checkpoint verified progress for authenticated approval and resume.
Unsupported drift
Refuse instead of improvise
If no configured path can establish the target or expected result, the workflow stops. OpenAdapt does not claim general adaptation to arbitrary application changes.
Availability and refusal depend on retained evidence and configuration. Identity checks cover armed steps only; system-of-record verification requires declared effects and a configured verifier. Read the measured limits.
From demonstration to operation
One governed workflow, end to end
OpenAdapt turns a demonstration into an inspectable workflow that moves from local development to governed operation without changing the workflow model.
- 01
Capture the workflow
Demonstrate a bounded, repeated task, including the evidence OpenAdapt needs to identify targets and verify outcomes.
- 02
Compile and policy-check
Turn the demonstration into an inspectable program with parameters, target evidence, postconditions, and an explicit OpenAdapt certification policy.
- 03
Run through the governed gate
The fail-closed run gate rechecks the exact bundle and selected policy. Healthy replay makes no model calls and produces structured evidence.
- 04
Resolve change under governance
Re-resolve from retained evidence, propose a reviewable repair when needed, and stop when configured verification fails.
One execution model across your stack
Built for the interfaces your work depends on
From modern browser apps to legacy Windows and remote desktops, workflows stay inspectable, policy-bound, and governed by explicit verification.
Web applications
Compile DOM, accessibility, visual, and interaction evidence into deterministic browser workflows.
Windows applications
Use structured UI Automation with retained visual evidence to operate legacy desktop applications.
RDP, Citrix & VDI
Carry the same policy, verification, repair, and audit model into remote application environments.
Choose the execution boundary
Local engine
Build, inspect, and run qualified workflows on your own infrastructure with the MIT-licensed engine.
View the engineManaged browser execution
Operate approved browser workflows through the hosted control plane with run history, reports, usage, and governed updates.
See hosted optionsCustomer-controlled deployment
Keep runtime data inside a qualified customer boundary when the workflow involves regulated data, private systems, or deployment-specific effect checks.
Review the security boundaryEvery production workflow is qualified against its target application and environment. Technical teams can review the qualification evidence, engine limits and hosted architecture.
Measured evidence for repeated browser work
Repeated work should not pay an agent to rethink the same task.
7.6× faster
median workflow time than the computer-use agent
$0 model cost
on a healthy compiled replay
0 model calls
on a healthy compiled replay
In a bounded browser benchmark, both approaches completed every tested run. OpenAdapt's median compiled replay was 7.6× faster and incurred no model cost on healthy runs. This benchmark measures speed and model cost for one task; it is not a production reliability claim.
Figures are copied verbatim from the published results file at the pinned commit and re-rendered at build time. The claims on this page are checked by automated truth tests.
Safety
Configured safeguards refuse instead of guessing.
OpenAdapt can require identity and effect evidence before a consequential step, then halt for an operator when verification is ambiguous. That protection applies only where the workflow is configured to check it; a success screen alone is not proof that a write reached the right system or record.
Who it's for
Teams closing a UI-only last-mile gap
OpenAdapt is built for high-volume workflows with structured inputs, established business logic, and a final write trapped behind a user interface. Demonstrate that last mile once and compile it into an inspectable program with explicit identity, effect, policy, and deployment boundaries. Healthy replay makes no model calls.
Automation teams & BPO operators
- High-volume repeated operations with structured inputs, established business logic, and a UI-only last-mile gap that can be checked against an independent effect source of truth.
Example: Insurance claims reference
RCM & vertical-software vendors
- Products with supported APIs for the core path and a bounded UI-only step at the edge, where volume and a separate system of record make verification practical.
Example: Healthcare workflow reference
Regulated enterprise operations
- Governed teams that already know the inputs and rules, repeat the task at material volume, and can verify the external effect independently of the GUI run.
Example: Lending operations reference
Launch options
Run it yourself or launch with us
Run the MIT-licensed engine yourself, use managed browser execution, or qualify a customer-controlled deployment. Hosted prices are confirmed by Stripe before payment.
Open Source
FreeMIT
For builders and self-hosters who want it running on their own machines.
- Browser artifacts stay local unless you explicitly push
- Deterministic re-resolution with auditable diffs
- Policy certification, fail-closed run gate, and reports
- MIT-licensed engine and CLI
pip install openadapt
Managed browser
Hosted
$500.00/month
OpenAdapt Cloud
Up to 10,000 workflow runs/month
Bring an approved browser workflow to a managed control plane for repeat execution, reporting, and governed updates.
- Managed execution of approved browser workflows
- Deterministic healthy replay with zero model calls
- Run history, failure reports, usage, and governed updates
- Sanitized uploads admitted under declared policy
- Price and billing period confirmed in Stripe
Hosted upload accepts an approved sanitized copy, not the original recording. Live screens can contain sensitive data again; workflows that expose PHI require a separately qualified customer-controlled boundary. Review the security boundary.
By subscribing, you agree to the Terms of Service and acknowledge the Privacy Notice.
Regulated deployment
Enterprise
Contact sales
For consequential workflows that require a customer-controlled data boundary. We qualify the substrate, artifact policy, effect oracle, and operating model before production use.
- Qualify the substrate and safety boundary first
- Scope one workflow and one measurable outcome
- Execute in the customer-controlled environment
- Identity and effect checks configured per deployment
- Sanitized derivatives may cross approved boundaries
- Runtime PHI remains in the trusted execution environment
- Deployment, support, and compliance terms documented in scope
Read our security posture: on-prem data handling, what is and isn't certified yet, and how to report a vulnerability.
Evaluate a workflowThe hosted subscription price shown above comes directly from Stripe and is confirmed again at checkout. Regulated deployment and service terms are scoped separately.
Open source
MIT licensed. Install it and read the code.
pip install openadapt is the stable end-user entry point. The openadapt-flow engine records a workflow, compiles it into a reviewable program, and replays it locally with no model calls on a healthy run.
Install the browser workflow CLI
One command installs the OpenAdapt launcher and governed workflow compiler. No account or hosted service is required.
Install
$pip install openadapt
The end-to-end browser loop
Try the whole loop right now against the bundled demo app: record, compile, inspect, certify, replay, and induce known test drift. No account or cloud service. Once it is installed, your workflow data stays on your machine. One heads-up on first run: the first demo-record or replay downloads a bundled Chromium (~150 MB) once, so that step takes a few minutes, and on Linux you may need playwright install-deps first.
pip install openadaptInstall OpenAdaptopenadapt flow demo-record --out recRecord yourself doing the taskopenadapt flow compile rec --out bundle --name my-taskTurn the recording into a workflowopenadapt flow lint bundleInspect identity, assertion, and risk coverage gapsopenadapt flow certify bundle --policy clinical-writeThe clinical gate refuses this demo bundle and exits non-zero — on purpose. Safeguards refuse instead of guessing. Re-run with --policy permissive to see a clean pass.openadapt flow replay bundleReplay it locally, with zero AI callsopenadapt flow replay bundle --drift themeExercise deterministic re-resolution on bundled test driftpip uninstall openadaptRemove the launcher when you are finishedEvery replay writes a step-by-step run report: what ran, what it saw, what re-resolved, and what halted. Compiler/runtime source and measured limits are in the openadapt-flow engine. Evaluating a regulated workflow? Evaluate a workflow.
PyPI Download Trends
Historical download statistics for OpenAdapt packages
1,648GitHub StarsView data source
8Packages
View:
Range:
Loading statistics...
Data sourced from PyPI OpenAdapt packages via pypistats.org API (data retained for ~180 days)
FAQ
Frequently asked questions
- What is OpenAdapt?
- OpenAdapt is an open-source governed workflow compiler for repeated GUI work. You demonstrate a task, it compiles the trace into a deterministic local program, and configured verification decides whether UI drift can be re-resolved, needs a proposed repair, or must halt. A healthy replay makes no model calls.
- How is OpenAdapt different from RPA tools like UiPath?
- Conventional RPA is broad and mature, especially on Windows, but workflows are usually assembled around selectors and integrations. OpenAdapt targets the narrower case where work is repetitive and consequential but the interface is visual, variable, or integration-hostile. It compiles a demonstration and uses a resolution ladder under drift rather than asking a model to re-plan every run.
- How is OpenAdapt different from AI computer-use agents?
- A computer-use agent is appropriate for novel work because it can re-plan each run. OpenAdapt is for repeated work: healthy replay follows the compiled program locally with zero model calls. Under drift, deterministic structure, template, OCR, and geometry evidence run first. An optional model can propose a repair, but it does not make unsupported drift safe and remains subject to configured verification and policy.
- Does “repair” mean every UI change is handled automatically?
- No. A target may be re-resolved deterministically, an optional model may propose a repair, an operator may teach a correction, or the run may halt as unsupported. Available evidence, identity coverage, postconditions, policy, and verifier configuration determine which outcome is allowed. OpenAdapt does not claim general adaptation to arbitrary application changes.
- Does my data leave my machines?
- Self-hosted runs remain local by default. Hosted upload accepts an approved sanitized copy, not the original recording and not an assumption that compilation removed sensitive data. Live screenshots can contain sensitive data again, so they stay inside the declared managed, customer-controlled, or on-prem runtime boundary. See the security page for the exact admission and review controls.
- Is OpenAdapt free?
- The engine is MIT-licensed and free to use or modify. Managed browser execution is available as a $500/month subscription, with the price and billing period confirmed again in Stripe Checkout. Customer-controlled deployments are scoped separately because the substrate, data boundary, verifier, and operating responsibilities differ.
- Is managed hosted execution available?
- Yes. The hosted subscription provides managed execution for approved browser workflows, including run history, reports, usage, and governed workflow updates. Start the subscription from the pricing section, then qualify the workflow and its verification boundary during onboarding.
- What software does OpenAdapt work with?
- OpenAdapt targets repeated workflows across browser applications, Windows UI Automation, native macOS, and remote desktop environments. Managed subscriptions cover approved browser workflows. Private systems, regulated runtime data, Windows, macOS, RDP, and Citrix workflows are delivered through a scoped customer-controlled deployment.
Workflow qualification
Book a 30-minute automation fit call
Tell us the substrate, repetition, consequence of error, data boundary, and current verification path. We'll tell you whether it fits managed browser execution, a customer-controlled deployment, or neither.
Product updates and hosted launch information. This does not create an account or promise access.